ArticleOpen Access http://dx.doi.org/10.26855/acc.2026.09.009
Research on the Optimization of Payment Risk Dynamic Monitoring Models Driven by High-dimensional Behavioral Features
Zhaoning Zhang
Pixel Department, Google, Chicago, IL 60607, USA.
*Corresponding author: Zhaoning Zhang
Published: July 23, 2026
Abstract
With the increasing variety and concealment of fraudulent transaction methods, traditional payment risk monitoring techniques encounter serious difficulties in detecting problems like single feature dimensions, static judgment approaches, and low risk recognition precision. In this study, we construct a comprehensive high-dimensional behavioral feature system that covers user attributes, transaction sequences, device conditions, and usage habits, and preprocess the feature data through standardization, dimensionality reduction, and normalization to improve the data quality and effectiveness of the features. A dynamic feature updating strategy is designed to update and optimize the risk features in real time, and an adaptive risk weight optimization algorithm is used to adjust the weights of various behavioral features. A stratified dynamic monitoring module is also set up to carry out multi-level and detailed identification and early warning of payment risks. The experimental results indicate that the improved model can effectively decrease the false alarm and miss alarm rates in payment risk monitoring, increase the ability to identify concealed and emergent fraud risks, and enhance the real-time performance and accuracy of the dynamic monitoring of payment risks, thus providing technical support for the intelligent risk control of digital payment systems.
Keyword
Payment risk; dynamic monitoring; high-dimensional behavioral features; model optimization
References
[1] Crowley C, Stuck RA, Zifferblatt J, et al. A quantitative method for detecting organization-level variation in healthcare payment risk score coding intensity. Health Serv Outcomes Res Methodol. 2026;(prepublish):1-20. doi:10.1007/S10742-026-00386-9.
[2] Rellensmann T, Engel S, Rommel J, et al. Collective contracts as a risk-sharing mechanism for result-based agri-environmental payments: experimental evidence. J Agric Econ. 2026;77(2):597-614. doi:10.1111/1477-9552.70034.
[3] Panturu A, Kleef VR, Eijkenaar F. Ex ante evaluation of risk adjustment models for prospective provider payment: a conceptual framework and empirical application. Eur J Health Econ. 2025;(prepublish):1-24. doi:10.1007/S10198-025-01871-7.
[4] Changchit C, Cutshall R, DeLatte G, et al. Exploring personality traits’ impact on risk perception in mobile payments. J Comput Inf Syst. 2025;65(6):672-687.
doi:10.1080/08874417.2024.2325417.
[5] Barbosa K, Fiuza E. Demand aggregation and payment risk effects on pooled procurement: evidence from the public healthcare sector. Q Rev Econ Finance. 2025;103:102011. doi:10.1016/J.QREF.2025.102011.
[6] Llanes IG, Salcedo A. Fuzzy non-payment risk management rooted in optimized household consumption units. Risks. 2025;13(4): 74. doi:10.3390/RISKS13040074.
[7] Olkiewicz A. How to mitigate the risk of late payments? The case of the largest polish companies selling electricity in 2018-2023. Energies. 2025;18(8):1918. doi:10.3390/EN18081918.
[8] Zheng J. Research on artificial intelligence-driven internet payment risk control system. Electron Sci Technol Appl. 2024;11(4).
doi:10.59429/ESTA.V11I4.8482.
Copyright
© 2026 by the author(s).
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND) license, which permits non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited and is not modified or adapted.
https://creativecommons.org/licenses/by-nc-nd/4.0/
How to cite this paper
Research on the Optimization of Payment Risk Dynamic Monitoring Models Driven by High-dimensional Behavioral Features
How to cite this paper: Zhaoning Zhang. (2026) Research on the Optimization of Payment Risk Dynamic Monitoring Models Driven by High-dimensional Behavioral Features. Advances in Computer and Communication, 7(3), 159-162.
DOI: http://dx.doi.org/10.26855/acc.2026.09.009